{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T05:51:05Z","timestamp":1781761865475,"version":"3.54.5"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,25]]},"DOI":"10.1109\/fg67764.2026.11557055","type":"proceedings-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T19:37:10Z","timestamp":1781725030000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Training-Free Semantic Multi-Object Tracking with Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Laurence","family":"Bonat","sequence":"first","affiliation":[{"name":"University of Trento,Department of Information Engineering and Computer Science,Trento,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesco","family":"Tonini","sequence":"additional","affiliation":[{"name":"University of Trento,Department of Information Engineering and Computer Science,Trento,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elisa","family":"Ricci","sequence":"additional","affiliation":[{"name":"University of Trento,Department of Information Engineering and Computer Science,Trento,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorenzo","family":"Vaquero","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler,Trento,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3522295"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization","author":"Banerjee"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/246309"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref6","article-title":"An Introduction to Vision-Language Modeling","author":"Bordes","year":"2024","journal-title":"ArXiv preprint, abs\/2405.17247"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00934"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1331"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2022.102317"},{"key":"ref10","article-title":"Xgrammar: Flexible and efficient structured generation engine for large language models","volume-title":"Proceedings of Machine Learning and Systems","volume":"7","author":"Dong"},{"key":"ref11","first-page":"41","article-title":"ican: Instance-centric attention network for human-object interaction detection","volume-title":"British Machine Vision Conference 2018, BMVC 2018","author":"Gao"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2024.3518613"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_35"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref15","first-page":"19730","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International Conference on Machine Learning, ICML 2023","volume":"202","author":"Li"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.398"},{"key":"ref18","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01375-2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075662"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0142"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref25","article-title":"D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement","author":"Peng","year":"2024","journal-title":"ArXiv preprint, abs\/2410.13842"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","volume":"139","author":"Radford"},{"key":"ref27","article-title":"SAM 2: Segment Anything in Images and Videos","author":"Ravi","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref29","first-page":"91","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume-title":"Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015","author":"Ren"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"ref31","article-title":"TransTrack: Multiple-Object Tracking with Transformer","author":"Sun","year":"2020","journal-title":"ArXiv"},{"key":"ref32","article-title":"The llama 3 herd of models","author":"Team","year":"2024","journal-title":"CoRR, abs\/2407.21783"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754770"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/icpr48806.2021.9412625"},{"key":"ref35","first-page":"448","article-title":"Lost and found: Overcoming detector failures in online multi-object tracking","author":"Vaquero","year":"2024","journal-title":"ECCV (73), volume 15131 of Lecture Notes in Computer Science"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref37","article-title":"Minilm: Deep self-attention distillation for task-agnostic compression of pretrained transformers","author":"Wang","year":"2020","journal-title":"NeurIPS"},{"key":"ref38","article-title":"Internvideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022","journal-title":"CoRR, abs\/2212.03191"},{"key":"ref39","article-title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","author":"Wang","year":"2025"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00653"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref42","first-page":"6787","article-title":"Videoclip: Contrastive pretraining for zero-shot video-text understanding","volume":"1","author":"Xu","year":"2021","journal-title":"EMNLP"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1177352.1177355"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02112"},{"key":"ref47","article-title":"Dense Video Object Captioning from Disjoint Supervision","author":"Zhou","year":"2023"},{"key":"ref48","article-title":"Minigpt4: Enhancing vision-language understanding with advanced large language models","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Zhu"}],"event":{"name":"2026 IEEE 20th International Conference on Automatic Face and Gesture Recognition (FG)","location":"Kyoto, Japan","start":{"date-parts":[[2026,5,25]]},"end":{"date-parts":[[2026,5,29]]}},"container-title":["2026 IEEE 20th International Conference on Automatic Face and Gesture Recognition (FG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11556508\/11556510\/11557055.pdf?arnumber=11557055","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T04:52:23Z","timestamp":1781758343000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11557055\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,25]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/fg67764.2026.11557055","relation":{},"subject":[],"published":{"date-parts":[[2026,5,25]]}}}